Comparison of prediction model using spatial discriminant analysis for marine water quality index in mangrove estuarine zones

Mohd Saiful Samsudin; Azman Azid; Saiful Iskandar Khalit; Muhamad Shirwan Abdullah Sani; Fathurrahman Lananan

doi:10.1016/j.marpolbul.2019.02.045

Comparison of prediction model using spatial discriminant analysis for marine water quality index in mangrove estuarine zones

Mar Pollut Bull. 2019 Apr:141:472-481. doi: 10.1016/j.marpolbul.2019.02.045. Epub 2019 Mar 9.

Authors

Mohd Saiful Samsudin¹, Azman Azid², Saiful Iskandar Khalit³, Muhamad Shirwan Abdullah Sani⁴, Fathurrahman Lananan³

Affiliations

¹ Faculty Bioresources and Food Industry, Universiti Sultan Zainal Abidin (UniSZA), Besut Campus, 22200 Besut, Terengganu, Malaysia; Dr. F.A.S. Technologies, Block D1, 2nd Floor UniSZA Digital Hub, UniSZA Besut Campus, 222000 Besut, Terengganu, Malaysia.
² Faculty Bioresources and Food Industry, Universiti Sultan Zainal Abidin (UniSZA), Besut Campus, 22200 Besut, Terengganu, Malaysia. Electronic address: azmanazid@unisza.edu.my.
³ Faculty Bioresources and Food Industry, Universiti Sultan Zainal Abidin (UniSZA), Besut Campus, 22200 Besut, Terengganu, Malaysia.
⁴ International Institute for Halal Research and Training, International Islamic University Malaysia, Selangor, Malaysia.

PMID: 30955758
DOI: 10.1016/j.marpolbul.2019.02.045

Abstract

The prediction models of MWQI in mangrove and estuarine zones were constructed. The 2011-2015 data employed in this study entailed 13 parameters from six monitoring stations in West Malaysia. Spatial discriminant analysis (SDA) had recommended seven significant parameters to develop the MWQI which were DO, TSS, O&G, PO₄, Cd, Cr and Zn. These selected parameters were then used to develop prediction models for the MWQI using artificial neural network (ANN) and multiple linear regressions (MLR). The SDA-ANN model had higher R² value for training (0.9044) and validation (0.7113) results than SDA-MLR model and was chosen as the best model in mangrove estuarine zone. The SDA-ANN model had also demonstrated lower RMSE (5.224) than the SDA-MLR (12.7755). In summary, this work suggested that ANN was an effective tool to compute the MWQ in mangrove estuarine zone and a powerful alternative prediction model as compared to the other modelling methods.

Keywords: Artificial neural networks; Discriminant analysis; Mangrove estuarine zone; Marine water quality; Multiple linear regression.

MeSH terms

Discriminant Analysis
Estuaries*
Linear Models
Malaysia
Models, Theoretical*
Neural Networks, Computer
Water Quality*
Wetlands*